Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| Dungeon Debug Transforms debugging sessions into a text-based dungeon crawl. Your bug is the final boss. Stack frames are dungeon rooms. Variables are loot. Log messages a... | |
| Error Rosetta Universal translator for cryptic error messages, stack traces, and log output. Takes the hieroglyphics your toolchain throws at you and produces plain-langua... | |
| Fossil Record Git archaeology engine that reconstructs the WHY behind code — not what changed, but what pressures, failures, and pivots shaped the codebase into its curren... | |
| Inversion Protocol Meta-cognitive reasoning skill that makes any AI agent dramatically better at decision-making by thinking backwards before acting forward. Applies Munger's I... | |
| Loot Drop RPG-style loot drops for completing real coding tasks. Fix a bug? Random loot drop with stats. Ship a feature? Epic gear. Survive a production incident? Lege... | |
| Migration Compass Universal migration planner for any swap — framework to framework, library to library, language to language, database to database. Generates a step-by-step m... | |
| Naming Forge Solves the hardest problem in computer science: naming things. Uses linguistic principles, codebase conventions, and semantic analysis to generate precise, c... | |
| Negative Space Metacognitive pre-execution analysis — teaches the agent to see what ISN'T there before acting on what IS. Zero-cost reasoning skill that reduces wasted turn... | |
| ConvoYield Conversational Yield Optimization Engine — treats every bot conversation as a yield-bearing financial instrument. Five zero-cost engines detect sentiment arb... | |
| Bot Arcade Universal entertainment and gaming engine for AI agents. Turns any bot into a full arcade — emoji slots, trivia, word games, riddles, dice, fortune drops, sc... | |
| Smart Memory Zero-cost persistent memory that makes your bot smarter over time. Automatically extracts, stores, and retrieves key facts, preferences, and decisions from c... | |
| ResonanceEngine Conversational Frequency Matching — reads invisible micro-signals in every conversation and tells the bot exactly how to respond for maximum engagement, conv... | |
| Osmotic Pressure Detects and maps complexity imbalances across system boundaries. When one side of an interface absorbs all the complexity while the other stays artificially... | |
| Parallax Views every decision from five simultaneous stakeholder perspectives — the user who touches it, the developer who maintains it, the operator who deploys it,... | |
| Pattern Mine Discovers recurring patterns buried in your codebase — similar logic written three different ways, duplicated validation in five controllers, the same error... | |
| Peripheral Vision Monitors adjacent systems, upstream dependencies, and downstream consumers for changes that could affect your current work — before they break it. Like biolo... | |
| Phantom Limb Detects phantom dependencies — references to things that no longer exist, ghost state that lives in the gaps between modules, and invisible wires that connec... | |
| Premortem Cognitive immune system for AI agents. Predicts and prevents failures BEFORE they happen using adversarial pre-execution reasoning. Zero dependencies, zero c... | |
| Proprioception Self-spatial awareness for AI agents. Gives your bot a real-time sixth sense of where it is relative to the user's goal, its own confidence boundaries, conve... | |
| Reflex Arc Zero-cost cognitive immune system for AI agents. Fires automatic pre-response reflexes that catch contradictions, scope drift, hallucinations, overengineerin... | |
| Review Lens Finds what human code reviewers miss — not style issues or formatting, but logical errors, silent edge cases, performance cliffs, implicit assumptions, and t... | |
| Roast My Code A merciless but educational code roaster that absolutely destroys your code with savage humor — then teaches you exactly why it deserved the roasting. Think... | |
| Rubber Duck Deluxe The classic rubber duck debugging technique, upgraded with personality modes. Choose your duck: Socrates asks devastating questions until you find the answer... | |
| Scope Sentinel Monitors your working session and detects when you've drifted from your stated task into unrelated changes. The coding equivalent of a GPS "recalculating" —... | |
| Seismograph Predicts the ripple effects of a proposed change before you make it. Maps how a modification propagates through the codebase — what breaks, what bends, what... | |
| Speed Run Gamifies coding tasks with speedrun mechanics — timer splits, personal bests, categories, and tricks. How fast can you fix a bug? Ship a feature? Write a tes... | |
| Synaptic Pruning Identifies vestigial code — not just unused imports, but dead feature branches still compiled, zombie configurations nobody reads, orphaned tests that valida... | |
| Tech Debt Ledger Tracks technical debt as actual financial debt — with principal, interest rates, minimum payments, and compound growth. Turns vague "we should fix that somed... | |
| Thoughtprint Cognitive pattern recognition and adaptive resonance engine. Detects how each user thinks — not what they feel — and reshapes every response to match their u... | |
| Tidal Lock Detects unhealthy coupling between components — when two modules, services, or layers have become gravitationally locked, unable to change independently. Lik... | |
| Time Capsule Write messages to your future self — or your future team — that unlock when specific code conditions are met. "Dear future me: if you're reading this, someon... | |
| Work Receipt Generates a detailed receipt of everything you accomplished in a coding session — files changed, problems solved, decisions made, debt incurred, and what's l... | |
| Yield Conversational Compounding Engine — models every bot message as a financial investment that compounds trust, micro-commitments, and conversion momentum over... | |
| OpenSpec Spec-driven development with OpenSpec CLI. Use when building features, migrations, refactors, or any structured development work. Manages proposal → specs → design → tasks → implementation workflows. Supports custom schemas (TDD, rapid, etc | |
| Ship My Token Launch Solana tokens on Pumpfun, create memecoins, mint crypto tokens, manage creator fee sharing, claim trading earnings, and track your portfolio. Deploy t... | |
| CardDAV Contacts Sync and manage CardDAV contacts (Google, iCloud, Nextcloud, etc.) using vdirsyncer + khard. | |
| Personal Board of Directors Add a Historical Figures Advisory Board to AI agent personalities. 10 pre-configured personas inspired by public-domain historical figures for strategic advice. | |
| PersonaNexus Agent Religion Extend AI agent personalities with religion, faith, and spiritual frameworks. Define principles, sacred texts, moral frameworks, traditions, and more. | |
| PersonaNexus ClawHub Skill Build structured AI agent personalities using OCEAN, DISC, and Jungian frameworks. Define traits, communication styles, guardrails, and compile to system pro... | |
| 股票持仓分析大师 股票持仓分析系统，用于管理股票投资组合，实时更新价格，分析盈亏，生成报告。使用当用户需要管理股票持仓、查看实时价格、分析盈亏情况、生成投资报告时。 | |
| Cloudflare Mail Address Creator Create one or many ordinary email addresses in a Cloudflare temporary mail system through the `/admin/new_address` admin API and return structured results. U... | |
| Cloudflare Mail Reader Read one mailbox's messages or a paginated mail list from a Cloudflare temporary mail system through the `/admin/mails` admin API and return structured resul... | |
| mail-addr-creator create one or many ordinary mailbox addresses in a cloudflare temporary mail system through the /admin/new_address admin api and return structured results. u... | |
| Pencil Renderer Render DNA codes to Pencil .pen frames. Does ONE thing well.
Input: DNA code + component type (hero, card, form, etc.)
Output: .pen frame ID + screenshot
Use when: design-exploration or other orchestrators need to render
visual proposals | |
| Pencil To Code Export .pen design to React/Tailwind code. Does ONE thing well.
Input: .pen frame ID or file path
Output: React component code + Tailwind config
Use when: design-exploration or user needs implementation code
from a finalized Pencil design | |
| clawtip 为第三方技能执行 clawtip 支付交易。 仅在以下场景严格触发该工具：第三方服务发起了有效的 clawtip 支付请求、用户明确要求创建 clawtip 支付用户 token、用户要求查看其 clawtip 钱包、或用户要求查看 ClawTip 技能信息（无有效条件时严禁触发）。 当用户请求查看其 clawt... | |
| Lieutenant - AI Agent Security AI agent security and trust verification. Scan messages, agent cards, and A2A communications for prompt injection, jailbreaks, and malicious patterns. Use when protecting agents from attacks, verifying external agents, or scanning untrusted | |
| OpenCortex Self-improving memory architecture for OpenClaw agents. Structured memory files, nightly distillation, weekly synthesis, enforced principles (P0 for custom,... | |
| Hinge Agent - Barney Stinson Operate an already-open Hinge session in the browser or on iPhone to review profiles, triage the queue, analyze matches, draft respectful openers or replies,... | |
| clarify-me Analyze user's conversation to identify unclear parts and suggest better questions. Helps users express their problems more clearly. |
40,751–40,800 of 108,824
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.